A method, apparatus, electronic equipment, and vehicle for determining a recommended list of charging stations.

Abstract

This application discloses a method, apparatus, and vehicle for determining a charging pile recommendation list, relating to the fields of new energy charging technology and intelligent recommendation technology. The method includes: acquiring meter readings of electricity meters for each charging pile within a specified time period in a target area, and acquiring actual charging data from vehicle-to-everything (V2X) networks using the charging piles; calculating the charging coefficient for each charging pile based on the meter readings and the actual charging data; determining the vehicle's driving status and charging preferences; and determining a charging pile recommendation list by combining the charging coefficient, the vehicle's driving status, and the charging preferences. By considering users' personalized needs, a personalized recommendation list is generated to meet the diverse needs of different users, which not only improves the user experience but also enhances the accuracy and scientific rigor of the charging coefficient calculation.

Description

Technical Field

[0001] This application relates to the fields of new energy charging technology and intelligent recommendation technology, and in particular to a method for determining a charging pile recommendation list, a device for determining a charging pile recommendation list, a storage medium, and a vehicle. Background Technology

[0002] With the rapid development of the new energy commercial vehicle market, the construction and operation of charging infrastructure has become a key factor influencing industry promotion. However, the current new energy commercial vehicle charging market faces many prominent problems, which seriously affect users' charging experience and operational efficiency, and also hinder the healthy development of the industry.

[0003] Due to the inherent resistance of the wires and electrical components inside the charging pile, heat will inevitably be generated when current flows through it, resulting in energy consumption, or power loss. This is an objective physical phenomenon. The power loss rate is affected by a variety of factors, including the performance of the charging pile, the charging performance of the power battery, and the performance of the battery management system (BMS). Commercial vehicle batteries have large capacities and high costs per charge, which makes users more sensitive and concerned about the power loss issue.

[0004] Currently, the industry lacks an effective quantitative assessment and public disclosure mechanism for the power loss rate of charging piles. Users lack the right to know about the power loss of each charging pile and cannot make scientific choices based on power loss factors. At the same time, existing charging pile recommendations mostly rely on single factors such as distance and price, and lack quantitative recommendation basis that comprehensively considers core performance such as power loss rate and charging speed, resulting in insufficient practicality and scientific validity of the recommendation results. Summary of the Invention

[0005] The purpose of this invention is to provide a method, device, electronic device, storage medium, and vehicle for determining a recommended list of charging piles, at least to solve the problem of how to make scientific selections of charging piles based on power loss factors, and to solve a technical problem in how to comprehensively consider the quantitative recommendation criteria based on core performance such as power loss rate and charging speed.

[0006] This invention provides the following solution:

[0007] According to one aspect of the present invention, a method for determining a recommended list of charging stations is provided, comprising:

[0008] Obtain the electricity meter readings of each charging pile within a specified time period in the target area, and obtain the actual charging data of the vehicle network using the charging piles for charging.

[0009] Based on the meter readings and the actual charging data of the vehicle network, the charging coefficient of each charging pile is calculated.

[0010] Determine the vehicle's driving status and charging preferences;

[0011] A recommended list of charging stations is determined by combining the charging coefficient, the vehicle's driving status, and the charging preference.

[0012] Furthermore, the calculation of the charging coefficient for each of the charging piles includes:

[0013] The actual charging data and the meter reading data are preprocessed to determine standardized actual charging data and standardized meter reading data.

[0014] For each of the charging piles, calculate the basic ratio between the standardized actual charging data and the standardized electricity meter readings;

[0015] Based on the standardized actual charging data and the standardized electricity meter measurement data, the influencing factors are determined, and the weights and correction coefficients of the influencing factors are determined.

[0016] Based on the weights and the correction coefficients, the base ratio is corrected to determine the correction ratio.

[0017] The charging coefficient is determined by statistical analysis of the correction ratio.

[0018] Furthermore, the step of preprocessing the actual charging data and the meter reading data to determine standardized actual charging data and standardized meter reading data includes:

[0019] The actual charging data and the meter reading data are divided into subgroups, and abnormal data is detected in each subgroup. Multiple abnormal data in each subgroup are identified and removed to obtain valid actual charging data and valid meter reading data.

[0020] Based on the charging start timestamp and charging end timestamp in the valid actual charging data and the valid electricity meter measurement data, the valid actual charging data and the valid electricity meter measurement data for the same charging time are aligned to obtain matching data;

[0021] The matching data is standardized to determine standardized actual charging data and standardized electricity meter readings.

[0022] Furthermore, determining the vehicle's driving status and charging preferences includes:

[0023] Obtain the vehicle's historical GPS driving trajectory and charging station historical usage data;

[0024] Based on the GPS historical driving trajectory and the charging pile historical usage data, determine the mapping relationship between the vehicle driving status and the charging preference;

[0025] Based on the vehicle's current GPS driving trajectory, the spatial activity range of the vehicle is quantified, and the vehicle's driving status is determined.

[0026] Based on the vehicle's driving status and the mapping relationship, charging preferences are determined.

[0027] Furthermore, the step of quantifying the spatial activity range of the vehicle and determining its driving status based on its current GPS driving trajectory includes:

[0028] Based on the GPS driving trajectory after removing abnormal trajectory points, a trajectory point set is constructed, and the spatial geometric centroid of the vehicle is calculated based on the trajectory point set.

[0029] Calculate the distance from each trajectory point in the trajectory point set to the spatial geometric centroid, and determine the distance set;

[0030] Based on the specified quantile value of the distance set, the activity radius of the vehicle is determined, and the proportion of trajectory points corresponding to the activity radius is determined;

[0031] Determine the activity radius threshold and concentration threshold;

[0032] The vehicle's driving status is determined by comparing the activity radius with the activity radius threshold, and by comparing the proportion of trajectory points with the concentration threshold.

[0033] Furthermore, the step of comparing the activity radius and the activity radius threshold, and comparing the trajectory point percentage and the concentration threshold to determine the vehicle driving state includes:

[0034] In response to the activity radius being less than or equal to the activity radius threshold and the proportion of trajectory points being greater than or equal to the concentration threshold, the vehicle's driving state is determined to be a short-distance driving state.

[0035] or

[0036] In response to the activity radius being greater than the activity radius threshold and the proportion of trajectory points being less than the concentration threshold, the vehicle's driving state is determined to be a long-distance driving state.

[0037] Furthermore, the step of determining the recommended list of charging stations by combining the charging coefficient, the vehicle driving status, and the charging preference includes:

[0038] Based on the vehicle's driving status, determine the proportional relationship between the charging preference weight and the vehicle driving status weight, as well as the comprehensive charging coefficient;

[0039] Based on the aforementioned proportional relationship and the comprehensive charging coefficient, a comprehensive recommendation index is determined;

[0040] A recommended list of charging stations is determined based on the comprehensive recommendation index.

[0041] Furthermore, the method also includes:

[0042] The actual charging data, the electricity meter reading data, and the GPS historical driving trajectory are updated using a sliding window algorithm.

[0043] Based on the updated actual charging data, the electricity meter reading data, and the GPS historical driving trajectory, the vehicle's driving status is re-determined;

[0044] Based on the redefined vehicle driving state, update the activity radius threshold, the concentration threshold, and the proportional relationship between the charging preference weight and the vehicle driving state weight.

[0045] According to a second aspect of the present invention, a device for determining a recommended list of charging stations is provided, comprising:

[0046] The data acquisition module is used to acquire the metering data of each charging pile in the target area for a specified time period, and to acquire the actual charging data of the vehicle network using the charging piles.

[0047] The data calculation module is used to calculate the charging coefficient of each charging pile based on the meter readings and the actual charging data of the vehicle network.

[0048] The data determination module is used to determine the vehicle's driving status and charging preferences;

[0049] The list recommendation module is used to determine a list of recommended charging stations by combining the charging coefficient, the vehicle driving status, and the charging preference.

[0050] According to three aspects of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0051] The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of determining the charging station recommendation list.

[0052] According to four aspects of the present invention, a computer-readable storage medium is provided, comprising: storing a computer program executable by an electronic device, wherein when the computer program is run on the electronic device, the electronic device performs the steps of a method for determining a charging station recommendation list.

[0053] According to five aspects of the present invention, a vehicle is provided, comprising:

[0054] Electronic equipment used to implement the steps of determining the recommended list of charging stations;

[0055] The processor runs a program that, when running, executes the steps of determining the charging station recommendation list based on data output from the electronic device.

[0056] Storage medium for storing a program that, when running, executes the steps of a method to determine a recommended list of charging stations based on data output from an electronic device.

[0057] The above solution achieves the following beneficial technical effects:

[0058] This application determines the vehicle's driving status and charging preferences based on electricity meter readings and actual vehicle network charging data. Therefore, in calculating the charging coefficient of each charging pile, the power loss rate of each charging pile is fully considered by combining electricity meter readings and actual vehicle network charging data. This allows users to clearly understand the power loss-related performance of each charging pile and provides a quantitative basis for users to select charging piles.

[0059] This application combines charging coefficient, vehicle driving status, and charging preferences to determine a recommended list of charging piles, constructing a multi-dimensional and dynamic charging coefficient evaluation system. By taking into account users' personalized needs, it generates a personalized recommendation list to meet the differentiated needs of different users. This not only improves the user experience but also enhances the accuracy and scientific nature of charging coefficient calculation, making the recommendation results more convincing. Attached Figure Description

[0060] Figure 1 This is a flowchart of a method for determining a recommended list of charging piles provided by one or more embodiments of the present invention.

[0061] Figure 2 This is a schematic diagram of a charging pile recommendation process provided in a specific embodiment of the present invention.

[0062] Figure 3 This is a structural diagram of a charging pile recommendation list determination device provided in one or more embodiments of the present invention.

[0063] Figure 4 This is a block diagram of an electronic device for determining a charging pile recommendation list provided in one or more embodiments of the present invention. Detailed Implementation

[0064] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] With the rapid development of the new energy commercial vehicle market, the construction and operation of charging infrastructure has become a key factor influencing industry promotion. However, the current new energy commercial vehicle charging market faces many prominent problems, which seriously affect users' charging experience and operational efficiency, and also hinder the healthy development of the industry.

[0066] In the new energy commercial vehicle charging market, the inherent resistance of the wires and electrical components inside the charging pile inevitably generates heat when current flows through, leading to energy consumption, or power loss—an objective physical phenomenon. Power loss rate is affected by various factors, including the performance of the charging pile itself; for example, the significant differences in the core components used between high-end and low-end charging piles directly result in substantial differences in power loss rate and reliability. Other factors include the charging performance of the power battery and the performance of the Battery Management System (BMS), such as the BMS's charging program settings and its own heat generation, all of which directly impact the power loss rate. Furthermore, the large battery capacity and high cost per charge for commercial vehicles make users more sensitive and concerned about power loss issues.

[0067] Currently, the industry generally adopts a pre-charge method for electricity loss, which means charging users based on the amount of electricity displayed on the charging pile's meter. However, the actual amount of electricity charged into the vehicle's battery by the user is often less than what the meter shows, and the cost of electricity loss is ultimately borne by the user. For new energy commercial vehicles with long annual mileage, the cost of electricity loss is considerable. Taking an electric heavy truck that travels 150,000 kilometers per year and consumes 1.6 kWh per kilometer as an example, if the electricity loss rate is 8%-10%, and calculated based on an average electricity price of 0.9 yuan / kWh, the annual cost of electricity loss can reach as high as 16,000 to 20,000 yuan, significantly increasing the user's operating costs.

[0068] Currently, the industry lacks an effective quantitative assessment and public disclosure mechanism for the power loss rate of charging piles. Users lack the right to know about the power loss of each charging pile and cannot make scientific choices based on power loss factors. At the same time, existing charging pile recommendations mostly rely on single factors such as distance and price, and lack quantitative recommendation basis that comprehensively considers core performance such as power loss rate and charging speed, resulting in insufficient practicality and scientific validity of the recommendation results.

[0069] Therefore, this application proposes a method for determining a recommended list of charging piles. By using electricity meter data and actual charging data from the vehicle network, taking into account the charging pile power loss rate, and comprehensively considering the personalized needs of users, a charging pile list is generated and determined for different users, so as to solve the above-mentioned problems existing in the prior art.

[0070] Figure 1 This is a flowchart of a method for determining a recommended list of charging piles provided by one or more embodiments of the present invention.

[0071] like Figure 1 The methods for determining the recommended list of charging stations shown include:

[0072] Step S1: Obtain the metering data of each charging pile in the target area for a specified time period, and obtain the actual charging data of the vehicle network using the charging piles.

[0073] In this embodiment, the meter readings of each charging pile within a specified time period in the target area, as well as the actual charging data of the vehicle network using the charging piles, are all comprehensive and accurate raw data.

[0074] The meter readings include the cumulative charging power of the charging pile, the amount of electricity displayed on the meter for a single charge, the charging timestamp, the charging pile number, and the latitude and longitude location information of the equipment.

[0075] Furthermore, by deploying edge computing nodes at the charging piles, the metering data of each charging pile can be collected, including but not limited to the charging pile number, equipment parameter information (power level, core component material rating, manufacturing date, cumulative usage time, etc.), the meter display of electricity for a single charge, charging start timestamp, charging end timestamp, latitude and longitude information, and charging vehicle identification number (VIN).

[0076] The actual charging data of the vehicle network includes the actual amount of electricity charged on a single charge for commercial vehicles, vehicle model, battery parameters, charging timestamp, vehicle identification number, and vehicle latitude and longitude.

[0077] Furthermore, the onboard T-Box terminal of the new energy commercial vehicle collects actual charging data during the charging process, including vehicle identification number (VIN), vehicle model, battery parameters (voltage platform, battery capacity, charging rate, battery health status (SOH), etc.), vehicle latitude and longitude data, actual charging amount per charge (uploaded through the vehicle network system via data displayed on the vehicle instrument panel), charging start time stamp, charging end time stamp, etc.

[0078] Step S2: Calculate the charging coefficient for each charging pile based on the electricity meter readings and the actual charging data from the vehicle network.

[0079] Data preprocessing is performed on actual charging data and electricity meter readings to determine standardized actual charging data and standardized electricity meter readings. Based on these standardized data, a dynamic weighted algorithm is then used to calculate the charging coefficient for each charging station.

[0080] Among them, the charging coefficient is a quantitative indicator that is the ratio of the actual amount of electricity charged by the commercial vehicle to the amount of electricity displayed by the charging pile meter after multi-dimensional correction. The higher the charging coefficient, the higher the recommendation index of the charging pile.

[0081] Step S3: Determine the vehicle's driving status and charging preferences.

[0082] In this embodiment, the vehicle's historical GPS driving trajectory and charging pile historical usage data can also be obtained to calculate the personalized needs of each vehicle, including the vehicle's driving status and charging preferences, so as to provide charging piles that meet the needs of different vehicles.

[0083] Step S4: Combine the charging coefficient, vehicle driving status, and charging preferences to determine the recommended list of charging stations.

[0084] Based on the charging coefficient of each charging station and the weight of the user's personalized needs (i.e., the weight of vehicle driving status and the weight of charging preference), a charging station recommendation list is generated through a sorting algorithm, and the recommendation results are fed back to the user.

[0085] Figure 2 This is a schematic diagram of a charging pile recommendation process provided in a specific embodiment of the present invention. Figure 2 As shown, data acquisition is first performed to obtain electricity meter readings and actual vehicle-to-everything (V2X) charging data. The acquired data is then preprocessed.

[0086] In the data preprocessing stage, outlier removal is achieved using a local anomaly detection method based on the same operating conditions to identify and remove abnormal charging records. Furthermore, the actual charging data and meter readings can be subgrouped, and anomaly detection can be performed on each subgroup to identify and remove various types of anomalies, resulting in valid actual charging data and valid meter readings.

[0087] Taking electricity meter data as an example, the charging records are first segmented by vehicle type (microvan / light truck / bus, etc.), battery capacity range (<50 kWh, 50–100, 100–150, 150–200, 200–250, 250–300, 300–350, 350–400, >400), and charging strategy (SOC 0–100%, 30–80%, 80–100%, etc.). Anomaly detection is performed within each group, and within each subgroup, anomaly detection algorithms (Robust LOF or k-NN anomaly score) are used to extract feature vectors. These feature vectors include the current charging amount, initial SOC, ending SOC, charging duration, average power, temperature, and time period.

[0088] For each record, calculate the LOF or k-NN distance. If the LOF > 1.5 (or the distance > 95th percentile), it is considered an anomaly. Physical boundary: If the charge amount > battery rated capacity × 1.05, it is directly considered an anomaly.

[0089] Minimum values: Charge amount < 1 kWh and charging time > 30 min are considered "virtual charging" or data truncation and should be discarded.

[0090] This allows us to obtain valid actual charging data and valid electricity meter readings.

[0091] Data alignment uses a timestamp matching algorithm to correlate the meter readings for the same charging event with the actual charging data from the vehicle network. Furthermore, based on the charging start and end timestamps and the vehicle's VIN, it precisely matches the valid actual charging data with the valid meter readings for the same charging event, obtaining matched data. This ensures that the meter readings for each charging event correspond exactly to the actual amount charged, avoiding calculation errors caused by data misalignment.

[0092] Data standardization employs the Z-score standardization method to convert matching data with different dimensions into standardized data under a unified standard, thereby determining standardized actual charging data and standardized electricity meter measurement data.

[0093] Based on the established standardized actual charging data and standardized electricity meter readings, a basic ratio between the standardized actual charging data and the standardized electricity meter readings is calculated. This basic ratio represents the ratio for a single charging session. For the j-th charging event at the i-th charging pile, the basic ratio is: R_ij = Q_ij^act / Q_ij^met, where Q_ij^act is the actual amount of electricity charged to the commercial vehicle during the j-th charging session at the i-th charging pile, and Q_ij^met is the amount of electricity displayed on the meter during the j-th charging session at the i-th charging pile. The basic ratio R_ij directly reflects the proportional relationship of electricity loss during a single charging session; a larger R_ij indicates a relatively smaller electricity loss during a single charging session.

[0094] Furthermore, based on standardized actual charging data and standardized electricity meter readings, influencing factors are determined. These factors include charging pile equipment parameters, battery parameters, charging power, and charging environment. For example, the weights of the charging pile equipment parameters and battery parameters are determined as ω1, ω2, ω3, and ω4, respectively. The initial weights of each influencing factor are determined using the Analytic Hierarchy Process (AHP) combined with the entropy weight method. Then, based on historical data within a preset time period, the Adaptive Particle Swarm Optimization (APSO) algorithm is used to dynamically correct the initial weights, resulting in the final dynamic weight vector W = [ω1, ω2, ω3, ω4].

[0095] The correction coefficients for each influencing factor are calculated separately. For example, the correction coefficient C1_i for charging pile equipment parameters is obtained by constructing a linear regression model based on the charging pile's power level, core component material rating, and service life. The correction coefficient C2_ij for battery parameters is obtained by predicting the voltage platform, charging rate, and state of health (SOH) of the commercial vehicle battery using a BP neural network model. The correction coefficient C3_ij for charging power is obtained by constructing an exponential function based on the ratio of the average charging power to the rated charging power during the charging process. The correction coefficient C4_ij for the charging environment is obtained by mapping the ambient temperature and humidity during charging using a Gaussian kernel function.

[0096] The base ratio is adjusted by using the weight of each influencing factor and its corresponding correction coefficient to determine the correction ratio. Specifically, the single-charge correction ratio R'_ij for the i-th charging pile can be calculated using a weighted product model, where R'_ij = R_ij × (C1_i^ω1 × C2_ij^ω2 × C3_ij^ω3 × C4_ij^ω4).

[0097] Statistical analysis is performed on the corrected ratios of all single charging cycles for the i-th charging pile within a preset time period. The M-estimation method in robust estimation is used to obtain the final charging coefficient.

[0098] This embodiment calculates a charging coefficient by combining electricity meter readings and actual vehicle network charging data, taking into full account the charging pile's power loss rate. By scientifically calculating and displaying this charging coefficient to the user, users can clearly understand the power loss-related performance of each charging pile, providing a quantitative basis for their charging pile selection.

[0099] In this embodiment, the vehicle's historical GPS driving trajectory and the vehicle's historical charging station usage data can also be obtained. These GPS historical driving trajectory and charging station historical usage data can then be used to determine the mapping relationship between the vehicle's driving status and charging preferences. Charging preferences may include charging speed preferences, charging cost preferences, and charging station distance preferences. For example, short-distance vehicle users may prioritize distance and cost, while long-distance vehicle users may prioritize speed and route suitability.

[0100] By analyzing the vehicle's current GPS trajectory, the spatial activity range of the vehicle is quantified, and the vehicle's driving status is determined, including both short-distance and long-distance driving status. Furthermore, by analyzing the vehicle's driving status and its mapping relationship, the current charging preference of the vehicle is determined.

[0101] The vehicle's driving status can be determined through the following methods.

[0102] Based on the GPS driving trajectory after removing abnormal trajectory points, a trajectory point set is constructed, and the spatial geometric centroid of the vehicle is calculated based on the trajectory point set. For example, for commercial vehicles with the same VIN, the spatial geometric centroid is calculated based on the constructed complete trajectory point set P = {(lng1, lat1), (lng2, lat2), ..., (lngn, latn)}, where lng represents longitude and lat represents latitude. The longitude of the spatial geometric centroid is: lon_center = (1 / n) × Σlng_i, and the latitude is: lat_center = (1 / n) × Σlat_i. This embodiment uses weighted centroid calculation, with the duration of the vehicle's stay at each trajectory point as the weight w_i. The corrected spatial geometric centroid formula is: lon_center = (Σw_i × lng_i) / Σw_i, lat_center = (Σw_i × lat_i) / Σw_i. The corrected spatial geometric centroid more closely matches the vehicle's actual core activity area.

[0103] It can also calculate the weighted centroid of the trajectory point set, with the weighting factor being the dwell time or frequency of the vehicle at each trajectory point. The calculated weighted centroid can replace the spatial geometric centroid for subsequent calculations.

[0104] The Haversine formula is used to calculate the distance from each trajectory point in the trajectory point set to the spatial geometric centroid, thus determining the distance set. Further, the method for calculating the spherical distance d_i from each trajectory point to the spatial geometric centroid is as follows: after converting latitude and longitude to radians, the longitude difference Δlng and the latitude difference Δlat are calculated. Using a = sin²(Δlat / 2) + cos(lat_i) × cos(lat_center) × sin²(Δlng / 2) and c = 2 × asin(√a), we obtain d_i = 6371 × c (the average radius of the Earth R = 6371 km).

[0105] Based on a specified quantile value of the distance set, the vehicle's activity radius is determined, and the percentage of trajectory points corresponding to that radius is also determined. The specified quantile value can be the 90th, 80th, or 60th quantile value of the distance set, etc., and can be selected according to the actual situation.

[0106] Generally, extreme outliers in the distance set are filtered using the interquartile range (IQR) rule, and the 90th percentile of the filtered distance set is taken as the core activity radius R_trans. Simultaneously, the 60th percentile value R is calculated. 60 80th percentile R 80 and the proportion P of trajectory points within the corresponding radius 60 P 80 P 90Thus, the concentration index is determined based on the proportion of trajectory points corresponding to the activity radius.

[0107] The activity radius threshold is determined based on the selected activity radius, and the concentration threshold is determined based on the concentration index.

[0108] If the activity radius is less than or equal to the activity radius threshold and the proportion of trajectory points is greater than or equal to the concentration threshold, the vehicle's driving state is determined to be short-distance driving. For example, in an urban delivery scenario, the thresholds R_threshold = 20km and P_threshold = 90% are set; if R_trans ≤ 20km and P... 90 If the percentage is ≥90%, it is determined to be a short-distance driving condition.

[0109] If the activity radius is greater than the activity radius threshold and the proportion of trajectory points is less than the concentration threshold, the vehicle's driving status is determined to be long-distance driving. For example, R_trans > 50km (trunk logistics threshold) and P 90 If the mileage is less than 80%, it is considered a long-distance driving condition.

[0110] For example, a certain new energy logistics vehicle VIN: XXXX has a core activity radius R_trans=15km, P 90 =95%, judged as short-distance travel; a certain trunk line freight truck R_trans=85km, P 90 =60%, indicating a long-distance driving condition.

[0111] After determining the vehicle's driving state, the weight ω5 for long-distance and short-distance adaptation can also be determined. Therefore, the dynamic weight vector W = [ω1, ω2, ω3, ω4, ω5]. ω5 is set to 0.1 for short-distance driving and 0.15 for long-distance driving (a 5% increase in weight). The initial weights are determined using AHP and entropy weighting methods, and after correction by the APSO algorithm, the final weight vectors are W = [0.25, 0.2, 0.2, 0.2, 0.15] (long-distance driving state) and W = [0.27, 0.22, 0.21, 0.2, 0.1] (short-distance driving state). The correction coefficient corresponding to the weight of long-distance and short-distance adaptation is C5_ij. Among them, short-distance vehicles are adapted to low-speed fast charging piles in cities, and the value of C5_ij ranges from 1.0 to 1.1 (prioritizing low-power loss low-speed charging piles); long-distance vehicles are adapted to high-speed fast charging piles, and the value of C5_ij ranges from 1.1 to 1.2 (prioritizing high-power, low-power loss high-speed charging piles). The specific values ​​are obtained by fitting historical charging data.

[0112] Furthermore, based on the determined weight ω5 for long-distance and short-distance adaptation, and the corresponding correction coefficient C5_ij, the comprehensive charging coefficient is determined. The comprehensive charging coefficient can be calculated by setting the corrected ratio as R''_ij = R_ij × (C1_i^ω1 × C2_ij^ω2 × C3_ij^ω3 × C4_ij^ω4 × C5_ij^ω5), removing outliers using box plot rules, and then averaging the results to obtain the comprehensive charging coefficient R_icomp, which is updated daily.

[0113] Based on the vehicle's driving status, the proportional relationship between charging preference weight and vehicle driving status weight is determined. Specifically, the charging pile distance preference weight is calculated based on the straight-line distance or planned driving distance between the vehicle's current latitude and longitude and the charging pile's latitude and longitude. For long-distance trips, the planned driving distance is prioritized (suitable for cross-regional routes), while for short-distance trips, the straight-line distance is prioritized (suitable for urban commuting). User ratings for various needs are obtained through the user interface to determine the personalized need weight vector.

[0114] For example, short-distance vehicle users prioritize distance and cost, with distance preference weight v3 set to 0.4, cost preference weight v2 set to 0.3, and speed preference weight v1 set to 0.3. Long-distance vehicle users prioritize speed and route suitability, with speed preference weight v1 set to 0.4, distance preference weight v3 set to 0.3 (calculated based on planned driving distance), and cost preference weight v2 set to 0.3.

[0115] Therefore, based on the proportional relationship and the comprehensive charging coefficient, a comprehensive recommendation index can be determined. The formula for calculating the comprehensive recommendation index is as follows:

[0116] S_i = α×R_icomp + β×(v1×S_speed_i + v2×S_cost_i + v3×S_dist_i) +γ×C5_ij

[0117] Where S_i represents the comprehensive recommendation index of the i-th charging pile, S_speed_i represents the charging speed of the i-th charging pile, S_cost_i represents the charging cost of the i-th charging pile, S_dist_i represents the charging distance to the i-th charging pile, γ represents the long-distance / short-distance adaptation factor, and α and β are dynamically adjusted according to the percentage of the battery's current remaining usable capacity to its rated capacity (SOC) and driving status. For example, for long-distance vehicles with SOC < 30% and navigation mileage > 150km, α = 0.25, β = 0.63, γ = 0.12, and priority is given to adapting to high-speed fast charging piles.

[0118] Where S_speed_i = Q_met / Δt, Q_met represents the amount of charge within the target time range, and Δt is the charging time.

[0119] Based on the determined comprehensive recommendation index, the recommended charging stations are arranged in descending order of the comprehensive recommendation index to form a charging station recommendation list. This list can display the top 5 recommended charging stations along with their corresponding charging coefficient, charging speed, navigation time, and other information. For example, for short-distance travel, vehicles are given priority to low-cost, low-power-loss charging stations within their core activity radius (e.g., within 20km); for long-distance travel, vehicles are given priority to highway service areas and intercity fast-charging stations along their travel route (based on the planned route).

[0120] A multi-dimensional and dynamic charging coefficient evaluation system is constructed, taking into account users' personalized needs. The charging coefficient is combined with factors such as charging speed, charging cost, distance from charging piles, and long and short driving scenarios to generate a personalized recommendation list. This not only meets the differentiated needs of different users and improves the user experience, but also enhances the accuracy and scientific nature of charging coefficient calculation, making the recommendation results more convincing.

[0121] In this embodiment, a sliding window algorithm can also be used to continuously update actual charging data, meter readings, and historical GPS driving trajectories. Based on the updated actual charging data, meter readings, and historical GPS driving trajectories, the vehicle's driving status is redefined. According to the redefined vehicle driving status, the activity radius threshold, concentration threshold, and the proportional relationship between charging preference weight and vehicle driving status weight are updated, thereby achieving iterative optimization of the charging pile recommendation list and generating an optimized charging pile recommendation list for users in real time. Specifically, according to a preset update cycle, the latest data is used to update and calculate the charging coefficient and long / short distance identification results. A sliding window algorithm is used to continuously update charging data and GPS trajectory data; after each new charging or trip, the long / short distance driving status identification results and charging coefficient are updated. The gradient descent method is used to iteratively optimize the dynamic weights, correction coefficient model, and long / short distance thresholds to ensure that the recommendation results adapt to changes in vehicle operating status.

[0122] By updating the charging pile recommendation list in real time, it can adapt to dynamic changes in data, ensuring the timeliness and reliability of the recommendation results, and has strong practical application value and market promotion prospects.

[0123] Figure 3 This is a structural diagram of a charging pile recommendation list determination device provided in one or more embodiments of the present invention.

[0124] like Figure 3 The charging pile recommendation list determination device shown includes: a data acquisition module, a data calculation module, a data determination module, and a list recommendation module.

[0125] The data acquisition module is used to acquire the metering data of each charging pile in the target area for a specified time period, and to acquire the actual charging data of the vehicle network using the charging piles.

[0126] The data calculation module is used to calculate the charging coefficient of each charging pile based on the electricity meter readings and the actual charging data of the vehicle network.

[0127] The data determination module is used to determine the vehicle's driving status and charging preferences;

[0128] The list recommendation module is used to determine a list of recommended charging stations by combining charging coefficient, vehicle driving status, and charging preferences.

[0129] The data calculation module is used to preprocess actual charging data and electricity meter readings to determine standardized actual charging data and standardized electricity meter readings; for each charging pile, it calculates the basic ratio of standardized actual charging data and standardized electricity meter readings; based on the standardized actual charging data and standardized electricity meter readings, it determines the influencing factors and their weights and correction coefficients; based on the weights and correction coefficients, it corrects the basic ratio to determine the corrected ratio; and it performs statistical analysis on the corrected ratio to determine the charging coefficient.

[0130] The data calculation module is used to divide the actual charging data and the meter reading data into subgroups, and to detect abnormal data in each subgroup. It identifies and removes various abnormal data in each subgroup to obtain valid actual charging data and valid meter reading data. Based on the charging start timestamp and charging end timestamp in the valid actual charging data and valid meter reading data, it aligns the valid actual charging data and valid meter reading data for the same charging time to obtain matched data. Finally, it standardizes the matched data to determine standardized actual charging data and standardized meter reading data.

[0131] The data determination module is used to acquire the vehicle's historical GPS driving trajectory and the charging pile's historical usage data; based on the historical GPS driving trajectory and the charging pile's historical usage data, it determines the mapping relationship between the vehicle's driving status and charging preferences; based on the vehicle's current GPS driving trajectory, it quantifies the vehicle's spatial activity range and determines the vehicle's driving status; based on the vehicle's driving status and the mapping relationship, it determines the charging preferences.

[0132] The data determination module is used to construct a trajectory point set based on the GPS driving trajectory after removing abnormal trajectory points, and calculate the spatial geometric centroid of the vehicle based on the trajectory point set; calculate the distance from each trajectory point in the trajectory point set to the spatial geometric centroid to determine the distance set; determine the vehicle's activity radius based on the specified quantile value of the distance set, and determine the proportion of trajectory points corresponding to the activity radius; determine the activity radius threshold and concentration threshold; compare the activity radius and the activity radius threshold, and compare the trajectory point proportion and concentration threshold to determine the vehicle's driving status.

[0133] The data determination module is used to determine the vehicle's driving status as short-distance driving when the activity radius is less than or equal to the activity radius threshold and the proportion of trajectory points is greater than or equal to the concentration threshold; or, in response to the activity radius being greater than the activity radius threshold and the proportion of trajectory points being less than the concentration threshold, to determine the vehicle's driving status as long-distance driving.

[0134] The list recommendation module is used to determine the proportional relationship between the charging preference weight and the vehicle driving status weight, as well as the comprehensive charging coefficient, based on the vehicle driving status; based on the proportional relationship and the comprehensive charging coefficient, a comprehensive recommendation index is determined; and based on the comprehensive recommendation index, a list of recommended charging stations is determined.

[0135] The data acquisition module is also used to update the actual charging data, meter readings, and GPS historical driving trajectories using a sliding window algorithm; based on the updated actual charging data, meter readings, and GPS historical driving trajectories, the vehicle driving status is redefined; and based on the redefined vehicle driving status, the activity radius threshold, concentration threshold, and the proportional relationship between the charging preference weight and the vehicle driving status weight are updated.

[0136] Figure 4 This is a block diagram of an electronic device for determining a charging pile recommendation list provided in one or more embodiments of the present invention.

[0137] like Figure 4 As shown, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0138] The memory stores a computer program that, when executed by a processor, causes the processor to perform steps of a method for determining a recommended list of charging stations.

[0139] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a method for determining a charging station recommendation list.

[0140] This application also provides a vehicle, including:

[0141] Electronic equipment for implementing the steps of a method for determining a recommended list of charging stations;

[0142] The processor runs a program that, when running, executes the steps of determining the charging station recommendation list based on data output from the electronic device.

[0143] Storage medium for storing a program that, when running, executes the steps of a method to determine a recommended list of charging stations based on data output from an electronic device.

[0144] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0145] The electronic device comprises a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory. The operating system can be any one or more computer operating systems that control the electronic device through processes, such as Linux, Unix, Android, iOS, or Windows. Furthermore, in this embodiment of the invention, the electronic device can be a smartphone, tablet computer, or other handheld device, or a desktop computer, portable computer, or other electronic device; there is no particular limitation in this embodiment.

[0146] In this embodiment of the invention, the executing entity for electronic device control can be an electronic device itself, or a functional module within an electronic device capable of calling and executing a program. The electronic device can obtain the firmware corresponding to the storage medium. This firmware is provided by the supplier, and different storage media may have the same or different firmware; no limitation is made here. After obtaining the firmware corresponding to the storage medium, the electronic device can write this firmware into the storage medium; specifically, it burns the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented using existing technology, and will not be elaborated upon in this embodiment of the invention.

[0147] Electronic devices can also obtain reset commands corresponding to the storage media. The reset commands corresponding to the storage media are provided by the supplier. The reset commands corresponding to different storage media can be the same or different, and no restrictions are imposed here.

[0148] At this time, the storage medium of the electronic device is a storage medium on which the corresponding firmware has been written. The electronic device can respond to the reset command corresponding to the storage medium on which the corresponding firmware has been written, thereby resetting the storage medium on which the corresponding firmware has been written according to the reset command. The process of resetting the storage medium according to the reset command can be implemented by existing technology and will not be described in detail in this embodiment of the invention.

[0149] For ease of description, the above devices are described separately by function as various units and modules. Of course, in implementing this application, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0150] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined.

[0151] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0152] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining a charging pile recommendation list, characterized in that, The recommended methods for charging piles include: Obtain the electricity meter readings of each charging pile within a specified time period in the target area, and obtain the actual charging data of the vehicle network using the charging piles for charging. Based on the meter readings and the actual charging data of the vehicle network, the charging coefficient of each charging pile is calculated. Determine the vehicle's driving status and charging preferences; A recommended list of charging stations is determined by combining the charging coefficient, the vehicle's driving status, and the charging preference. 2.The method of claim 1, wherein, The calculation of the charging coefficient for each of the charging piles includes: The actual charging data and the meter reading data are preprocessed to determine standardized actual charging data and standardized meter reading data. For each of the charging piles, calculate the basic ratio between the standardized actual charging data and the standardized electricity meter readings; Based on the standardized actual charging data and the standardized electricity meter measurement data, the influencing factors are determined, and the weights and correction coefficients of the influencing factors are determined. Based on the weights and the correction coefficients, the base ratio is corrected to determine the correction ratio. The charging coefficient is determined by statistical analysis of the correction ratio. 3.The method of claim 2, wherein, The step of preprocessing the actual charging data and the meter reading data to determine standardized actual charging data and standardized meter reading data includes: The actual charging data and the meter reading data are divided into subgroups, and abnormal data is detected in each subgroup. Multiple abnormal data in each subgroup are identified and removed to obtain valid actual charging data and valid meter reading data. Based on the charging start timestamp and charging end timestamp in the valid actual charging data and the valid electricity meter measurement data, the valid actual charging data and the valid electricity meter measurement data for the same charging time are aligned to obtain matching data; The matching data is standardized to determine standardized actual charging data and standardized electricity meter readings.

4. The method for determining the recommended list of charging piles according to claim 1, characterized in that, Determining the vehicle's driving status and charging preferences includes: Obtain the vehicle's historical GPS driving trajectory and charging station historical usage data; Based on the GPS historical driving trajectory and the charging pile historical usage data, determine the mapping relationship between the vehicle driving status and the charging preference; Based on the vehicle's current GPS driving trajectory, the spatial activity range of the vehicle is quantified, and the vehicle's driving status is determined. Based on the vehicle's driving status and the mapping relationship, charging preferences are determined.

5. The method for determining the recommended list of charging piles according to claim 4, characterized in that, The step of quantifying the spatial activity range of the vehicle and determining the vehicle's driving status based on the vehicle's current GPS driving trajectory includes: Based on the GPS driving trajectory after removing abnormal trajectory points, a trajectory point set is constructed, and the spatial geometric centroid of the vehicle is calculated based on the trajectory point set. Calculate the distance from each trajectory point in the trajectory point set to the spatial geometric centroid, and determine the distance set; Based on the specified quantile value of the distance set, the activity radius of the vehicle is determined, and the proportion of trajectory points corresponding to the activity radius is determined; Determine the activity radius threshold and concentration threshold; The vehicle's driving status is determined by comparing the activity radius with the activity radius threshold, and by comparing the proportion of trajectory points with the concentration threshold.

6. The method for determining the recommended list of charging piles according to claim 5, characterized in that, The step of comparing the activity radius and the activity radius threshold, and comparing the trajectory point percentage and the concentration threshold to determine the vehicle driving status includes: In response to the activity radius being less than or equal to the activity radius threshold and the proportion of trajectory points being greater than or equal to the concentration threshold, the vehicle's driving state is determined to be a short-distance driving state. or In response to the activity radius being greater than the activity radius threshold and the proportion of trajectory points being less than the concentration threshold, the vehicle's driving state is determined to be a long-distance driving state.

7. The method for determining the recommended list of charging piles according to claim 6, characterized in that, The process of determining a recommended list of charging stations by combining the charging coefficient, the vehicle's driving status, and the charging preference includes: Based on the vehicle's driving status, determine the proportional relationship between the charging preference weight and the vehicle driving status weight, as well as the comprehensive charging coefficient; Based on the aforementioned proportional relationship and the comprehensive charging coefficient, a comprehensive recommendation index is determined; A recommended list of charging stations is determined based on the comprehensive recommendation index.

8. The method for determining the recommended list of charging piles according to claim 7, characterized in that, The method further includes: The actual charging data, the electricity meter reading data, and the GPS historical driving trajectory are updated using a sliding window algorithm. Based on the updated actual charging data, the electricity meter reading data, and the GPS historical driving trajectory, the vehicle's driving status is re-determined; Based on the redefined vehicle driving state, update the activity radius threshold, the concentration threshold, and the proportional relationship between the charging preference weight and the vehicle driving state weight.

9. A device for determining a recommended list of charging piles, characterized in that, The device for determining the recommended list of charging piles includes: The data acquisition module is used to acquire the metering data of each charging pile in the target area for a specified time period, and to acquire the actual charging data of the vehicle network using the charging piles. The data calculation module is used to calculate the charging coefficient of each charging pile based on the meter readings and the actual charging data of the vehicle network. The data determination module is used to determine the vehicle's driving status and charging preferences; The list recommendation module is used to determine a list of recommended charging stations by combining the charging coefficient, the vehicle driving status, and the charging preference.

10. A vehicle, characterized in that, include: An electronic device for implementing the steps of the charging pile recommendation list determination method as described in any one of claims 1 to 8; A processor that runs a program that, when the program is running, performs the steps of the charging pile recommendation list determination method as described in any one of claims 1 to 8 from data output by the electronic device. A storage medium for storing a program that, when running, performs the steps of the charging pile recommendation list determination method as described in any one of claims 1 to 8 on data output from an electronic device.

Images